Searcharxiv⌕ Search

arXiv subjects

Steffen Eger

Publications and source records attributed to Steffen Eger.

108 records · Page 6Linked to original sources
arXiv2018

Cross-lingual Argumentation Mining: Machine Translation (and a bit of Projection) is All You Need!

Argumentation mining (AM) requires the identification of complex discourse structures and has lately been applied with success monolingually. In this work, we show that the existing resources are, however, not adequate for assessing cross-lingual AM, due to their heterogeneity or lack of complexity. We therefore create suitable parallel corpora by (human and machine) translating a popular AM dataset consisting of persuasive student essays into German, French, Spanish, and Chinese. We then compare (i) annotation projection and (ii) bilingual word embeddings based direct transfer strategies for cross-lingual AM, finding that the former performs considerably better and almost eliminates the loss from cross-lingual transfer. Moreover, we find that annotation projection works equally well when using either costly human or cheap machine translations. Our code and data are available at \url{http://github.com/UKPLab/coling2018-xling_argument_mining}.

cs.CL↗
arXiv2018

Multi-Task Learning for Argumentation Mining in Low-Resource Settings

We investigate whether and where multi-task learning (MTL) can improve performance on NLP problems related to argumentation mining (AM), in particular argument component identification. Our results show that MTL performs particularly well (and better than single-task learning) when little training data is available for the main task, a common scenario in AM. Our findings challenge previous assumptions that conceptualizations across AM datasets are divergent and that MTL is difficult for semantic or higher-level tasks.

cs.CL↗
arXiv2017

What is the Essence of a Claim? Cross-Domain Claim Identification

Argument mining has become a popular research area in NLP. It typically includes the identification of argumentative components, e.g. claims, as the central component of an argument. We perform a qualitative analysis across six different datasets and show that these appear to conceptualize claims quite differently. To learn about the consequences of such different conceptualizations of claim for practical applications, we carried out extensive experiments using state-of-the-art feature-rich and deep learning systems, to identify claims in a cross-domain fashion. While the divergent perception of claims in different datasets is indeed harmful to cross-domain classification, we show that there are shared properties on the lexical level as well as system configurations that can help to overcome these gaps.

cs.CL↗
arXiv2017

Neural End-to-End Learning for Computational Argumentation Mining

We investigate neural techniques for end-to-end computational argumentation mining (AM). We frame AM both as a token-based dependency parsing and as a token-based sequence tagging problem, including a multi-task learning setup. Contrary to models that operate on the argument component level, we find that framing AM as dependency parsing leads to subpar performance results. In contrast, less complex (local) tagging models based on BiLSTMs perform robustly across classification scenarios, being able to catch long-range dependencies inherent to the AM problem. Moreover, we find that jointly learning 'natural' subtasks, in a multi-task learning setup, improves performance.

cs.CL↗
arXiv2017

EELECTION at SemEval-2017 Task 10: Ensemble of nEural Learners for kEyphrase ClassificaTION

This paper describes our approach to the SemEval 2017 Task 10: "Extracting Keyphrases and Relations from Scientific Publications", specifically to Subtask (B): "Classification of identified keyphrases". We explored three different deep learning approaches: a character-level convolutional neural network (CNN), a stacked learner with an MLP meta-classifier, and an attention based Bi-LSTM. From these approaches, we created an ensemble of differently hyper-parameterized systems, achieving a micro-F1-score of 0.63 on the test data. Our approach ranks 2nd (score of 1st placed system: 0.64) out of four according to this official score. However, we erroneously trained 2 out of 3 neural nets (the stacker and the CNN) on only roughly 15% of the full data, namely, the original development set. When trained on the full data (training+development), our ensemble has a micro-F1-score of 0.69. Our code is available from https://github.com/UKPLab/semeval2017-scienceie.

cs.CL↗
arXiv2017

On the Linearity of Semantic Change: Investigating Meaning Variation via Dynamic Graph Models

We consider two graph models of semantic change. The first is a time-series model that relates embedding vectors from one time period to embedding vectors of previous time periods. In the second, we construct one graph for each word: nodes in this graph correspond to time points and edge weights to the similarity of the word's meaning across two time points. We apply our two models to corpora across three different languages. We find that semantic change is linear in two senses. Firstly, today's embedding vectors (= meaning) of words can be derived as linear combinations of embedding vectors of their neighbors in previous time periods. Secondly, self-similarity of words decays linearly in time. We consider both findings as new laws/hypotheses of semantic change.

cs.CL↗
arXiv2016

Opinion dynamics and wisdom under out-group discrimination

We study a DeGroot-like opinion dynamics model in which agents may oppose other agents. As an underlying motivation, in our setup, agents want to adjust their opinions to match those of the agents of their 'in-group' and, in addition, they want to adjust their opinions to match the 'inverse' of those of the agents of their 'out-group'. Our paradigm can account for persistent disagreement in connected societies as well as bi- and multi-polarization. Outcomes depend upon network structure and the choice of deviation function modeling the mode of opposition between agents. For a particular choice of deviation function, which we call soft opposition, we derive necessary and sufficient conditions for long-run polarization. We also consider social influence (who are the opinion leaders in the network?) as well as the question of wisdom in our naive learning paradigm, finding that wisdom is difficult to attain when there exist sufficiently strong negative relations between agents.

cs.MA↗
arXiv2016

Still not there? Comparing Traditional Sequence-to-Sequence Models to Encoder-Decoder Neural Networks on Monotone String Translation Tasks

We analyze the performance of encoder-decoder neural models and compare them with well-known established methods. The latter represent different classes of traditional approaches that are applied to the monotone sequence-to-sequence tasks OCR post-correction, spelling correction, grapheme-to-phoneme conversion, and lemmatization. Such tasks are of practical relevance for various higher-level research fields including digital humanities, automatic text correction, and speech recognition. We investigate how well generic deep-learning approaches adapt to these tasks, and how they perform in comparison with established and more specialized methods, including our own adaptation of pruned CRFs.

cs.CL↗
arXiv2016

Language classification from bilingual word embedding graphs

We study the role of the second language in bilingual word embeddings in monolingual semantic evaluation tasks. We find strongly and weakly positive correlations between down-stream task performance and second language similarity to the target language. Additionally, we show how bilingual word embeddings can be employed for the task of semantic language classification and that joint semantic spaces vary in meaningful ways across second languages. Our results support the hypothesis that semantic language similarity is influenced by both structural similarity as well as geography/contact.

cs.CL↗
arXiv2016

Stirling's approximation for central extended binomial coefficients

We derive asymptotic formulas for central extended binomial coefficients, which are generalizations of binomial coefficients. To do so, we relate the exact distribution of the sum of independent discrete uniform random variables to the asymptotic distribution, obtained from the Central Limit Theorem and a local limit variant.

math.PR↗
arXiv2016

On the Number of Many-to-Many Alignments of Multiple Sequences

We count the number of alignments of $N \ge 1$ sequences when match-up types are from a specified set $S\subseteq \mathbb{N}^N$. Equivalently, we count the number of nonnegative integer matrices whose rows sum to a given fixed vector and each of whose columns lie in $S$. We provide a new asymptotic formula for the case $S=\{(s_1,\ldots,s_N) \:|\: 1\le s_i\le 2\}$.

math.CO↗
arXiv2016

Identities for partial Bell polynomials derived from identities for weighted integer compositions

We discuss closed-form formulas for the (n; k)-th partial Bell polynomials derived in Cvijovic. We show that partial Bell polynomials are special cases of weighted integer compositions, and demonstrate how the identities for partial Bell polynomials easily follow from more general identities for weighted integer compositions. We also provide short and elegant probabilistic proofs of the latter, in terms of sums of discrete integer-valued random variables. Finally, we outline further identities for the partial Bell polynomials.

math.CO↗
arXiv2016

Complex Decomposition of the Negative Distance kernel

A Support Vector Machine (SVM) has become a very popular machine learning method for text classification. One reason for this relates to the range of existing kernels which allow for classifying data that is not linearly separable. The linear, polynomial and RBF (Gaussian Radial Basis Function) kernel are commonly used and serve as a basis of comparison in our study. We show how to derive the primal form of the quadratic Power Kernel (PK) -- also called the Negative Euclidean Distance Kernel (NDK) -- by means of complex numbers. We exemplify the NDK in the framework of text categorization using the Dewey Document Classification (DDC) as the target scheme. Our evaluation shows that the power kernel produces F-scores that are comparable to the reference kernels, but is -- except for the linear kernel -- faster to compute. Finally, we show how to extend the NDK-approach by including the Mahalanobis distance.

cs.LG↗
arXiv2015

Some Elementary Congruences for the Number of Weighted Integer Compositions

An integer composition of a nonnegative integer $n$ is a tuple $(π_1,\ldots,π_k)$ of nonnegative integers whose sum is $n$; the $π_i$'s are called the parts of the composition. For fixed number $k$ of parts, the number of $f$-weighted integer compositions (also called $f$-colored integer compositions in the literature), in which each part size $s$ may occur in $f(s)$ different colors, is given by the extended binomial coefficient $\binom{k}{n}_{f}$. We derive several congruence properties for $\binom{k}{n}_{f}$, most of which are analogous to those for ordinary binomial coefficients. Among them is the parity of $\binom{k}{n}_{f}$, Babbage's congruence, Lucas' theorem, etc. We also give congruences for $c_{f}(n)$, the number of $f$-weighted integer compositions with arbitrarily many parts, and for extended binomial coefficient sums. We close with an application of our results to prime criteria for weighted integer compositions.

math.CO↗
arXiv2014

Corrections to the results derived in "A Unified Approach to Algorithms Generating Unrestricted and Restricted Integer Compositions and Integer Partitions"'; and a comparison of four restricted integer composition generation algorithms

In this note, I discuss results on integer compositions/partitions given in the paper "A Unified Approach to Algorithms Generating Unrestricted and Restricted Integer Compositions and Integer Partitions". I also experiment with four different generation algorithms for restricted integer compositions and find the algorithm designed in the named paper to be pretty slow, comparatively. Some of my comments may be subjective.

cs.DS↗
arXiv2013

(Failure of the) Wisdom of the crowds in an endogenous opinion dynamics model with multiply biased agents

We study an endogenous opinion (or, belief) dynamics model where we endogenize the social network that models the link (`trust') weights between agents. Our network adjustment mechanism is simple: an agent increases her weight for another agent if that agent has been close to truth (whence, our adjustment criterion is `past performance'). Moreover, we consider multiply biased agents that do not learn in a fully rational manner but are subject to persuasion bias - they learn in a DeGroot manner, via a simple `rule of thumb' - and that have biased initial beliefs. In addition, we also study this setup under conformity, opposition, and homophily - which are recently suggested variants of DeGroot learning in social networks - thereby taking into account further biases agents are susceptible to. Our main focus is on crowd wisdom, that is, on the question whether the so biased agents can adequately aggregate dispersed information and, consequently, learn the true states of the topics they communicate about. In particular, we present several conditions under which wisdom fails.

cs.SI↗
arXiv2012

Asymptotic normality of integer compositions inside a rectangle

Among all restricted integer compositions with at most $m$ parts, each of which has size at most $l$, choose one uniformly at random. Which integer does this composition represent? In the current note, we show that underlying distribution is, for large $m$ and $l$, approximately normal with mean value $\frac{ml}{2}$.

math.CO↗